Moneerh Aleedy1, Riham AlSmariy2, Wejdan Alsurayyi1* and Suad Almutairi1
1Information Technology Department, College of Computer and Information
Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
2Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
*Corresponding Author: Wejdan Alsurayyi, Information Technology Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
Received: February 07, 2024; Published: February 21, 2024
The gender recognition system by a sample of voice has an excellent mechanism based on many factors and features of sound signals like frequency, pitch, and loudness. This paper implements a machine to distinguish between the male's and female's voice. The experiments are implemented by two techniques to split speech dataset: train_test_split function and 10-fold Cross-Validation on the training set (after splitting the data into train and test set), to get the highest result and improve the model and make a comparison between them. Then, the K-best feature selection is used as a filtering method and Recursive Feature Elimination (RFE) as a wrapper method. This paper investigates various machine learning algorithms, such as logistic regression, random forest, SVM, gradient boosting, and decision tree. The performance was evaluated using different metrics: accuracy, recall, precision, F-score, and confusion-matrix. The results showed that splitting the dataset using 10-fold CV with RFE provides the best result for all ML algorithms and the best model is the random forest, it gives the highest percentage in all evaluation methods.
Keywords: Machine Learning; Voice; RFE; k-Best; Random Forest
Citation: Wejdan Alsurayyi., et al. “Gender Recognition by Voice Using Machine Learning".Acta Scientific Computer Sciences 6.3 (2024): 07-12.
Copyright: © 2024 Wejdan Alsurayyi., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.